/

/

AWS Bedrock

MODEL PROVIDER

AWS Bedrock

Models from Anthropic, Amazon, Meta, Mistral, and Cohere through Amazon Bedrock, billed and governed in your AWS account.

AWS Bedrock has 35 models available in SteelEngine with pricing, context window, and capability details.

MODELS

35

DEFAULT MODEL

Anthropic Claude Sonnet 4.5

PRICING

USD PER 1M TOKENS

MODELS

AWS Bedrock models in SteelEngine.

Recommended models come first. Open any model for its full price sheet, limits, and supported capabilities.

AWS Bedrock

Meta Llama 4 Scout 17B Instruct

Lower-priced model for high-volume classification, extraction, and routing. Reads up to 3.5M tokens of context in one call.

IN / 1M

$0.17

OUT / 1M

$0.66

CONTEXT

3.5M

AWS Bedrock

Anthropic Claude Opus 5.5

Higher-priced model for demanding generation and analysis. Reads up to 1M tokens of context in one call and writes up to 128k tokens. Released Sep 22, 2026.

IN / 1M

$4.4

OUT / 1M

$22

CONTEXT

1M

AWS Bedrock

Anthropic Claude Sonnet 5.5

Higher-priced model for demanding generation and analysis. Reads up to 1M tokens of context in one call and writes up to 128k tokens. Released Sep 28, 2026.

IN / 1M

$2.2

OUT / 1M

$11

CONTEXT

1M

AWS Bedrock

Anthropic Claude Haiku 5.5

Fast, lower-priced model for high-volume classification, extraction, and routing. Reads up to 1M tokens of context in one call and writes up to 128k tokens.

IN / 1M

$0.11

OUT / 1M

$0.55

CONTEXT

1M

AWS Bedrock

Anthropic Claude Fable 5.1

Higher-priced model for demanding generation and analysis. Reads up to 1M tokens of context in one call and writes up to 128k tokens. Released Sep 1, 2026.

IN / 1M

$11

OUT / 1M

$55

CONTEXT

1M

AWS Bedrock

Anthropic Claude Opus 5

Higher-priced model for demanding generation and analysis. Reads up to 1M tokens of context in one call and writes up to 128k tokens. Released Jul 24, 2026.

IN / 1M

$5.5

OUT / 1M

$27.5

CONTEXT

1M

AWS Bedrock

Anthropic Claude Sonnet 5

Higher-priced model for demanding generation and analysis. Reads up to 1M tokens of context in one call and writes up to 128k tokens. Released Jun 30, 2026.

IN / 1M

$2.2

OUT / 1M

$11

CONTEXT

1M

AWS Bedrock

Anthropic Claude Opus 4.8

Higher-priced model for demanding generation and analysis. Reads up to 1M tokens of context in one call and writes up to 128k tokens. Released May 28, 2026.

IN / 1M

$5.5

OUT / 1M

$27.5

CONTEXT

1M

AWS Bedrock

Anthropic Claude Opus 4.7

Higher-priced model for demanding generation and analysis. Reads up to 1M tokens of context in one call and writes up to 128k tokens. Released Apr 16, 2026.

IN / 1M

$5.5

OUT / 1M

$27.5

CONTEXT

1M

AWS Bedrock

Amazon Nova 2 Pro

Higher-effort variant for problems where answer quality matters more than latency or cost. Reads up to 1M tokens of context in one call.

IN / 1M

$1.375

OUT / 1M

$11

CONTEXT

1M

AWS Bedrock

Amazon Nova 2 Lite

Mid-priced, latency-focused model for chat, drafting, and tool calling. Reads up to 1M tokens of context in one call.

IN / 1M

$0.33

OUT / 1M

$2.75

CONTEXT

1M

AWS Bedrock

Amazon Nova Premier

Higher-priced model for demanding generation and analysis. Reads up to 1M tokens of context in one call.

IN / 1M

$2.5

OUT / 1M

$12.5

CONTEXT

1M

AWS Bedrock

Meta Llama 4 Maverick 17B Instruct

Lower-priced model for high-volume classification, extraction, and routing. Reads up to 1M tokens of context in one call.

IN / 1M

$0.24

OUT / 1M

$0.97

CONTEXT

1M

AWS Bedrock

Anthropic Claude Opus 4.5

Higher-priced model for demanding generation and analysis. Handles 200k tokens of context and writes up to 64k tokens. Opus is Anthropic’s largest Claude tier.

IN / 1M

$5

OUT / 1M

$25

CONTEXT

200k

AWS Bedrock

Anthropic Claude Sonnet 4.5

Higher-priced model for demanding generation and analysis. Handles 200k tokens of context and writes up to 64k tokens. Sonnet is Anthropic’s mid-size Claude tier.

IN / 1M

$3

OUT / 1M

$15

CONTEXT

200k

AWS Bedrock

Anthropic Claude Haiku 4.5

Mid-priced, latency-focused model for chat, drafting, and tool calling. Handles 200k tokens of context and writes up to 64k tokens.

IN / 1M

$1

OUT / 1M

$5

CONTEXT

200k

AWS Bedrock

Anthropic Claude Opus 4.1

The highest-priced model in the AWS Bedrock lineup, for the hardest generation and analysis work. Handles 200k tokens of context and writes up to 32k tokens.

IN / 1M

$15

OUT / 1M

$75

CONTEXT

200k

AWS Bedrock

Amazon Nova Pro

Higher-effort variant for problems where answer quality matters more than latency or cost. Handles 300k tokens of context.

IN / 1M

$0.8

OUT / 1M

$3.2

CONTEXT

300k

AWS Bedrock

Amazon Nova Lite

Fast, lower-priced model for high-volume classification, extraction, and routing. Handles 300k tokens of context.

IN / 1M

$0.06

OUT / 1M

$0.24

CONTEXT

300k

AWS Bedrock

Mistral Large 3 675B Instruct

Mid-priced general model for drafting, summarizing, and tool calling. Handles 256k tokens of context and writes up to 32k tokens.

IN / 1M

$0.5

OUT / 1M

$1.5

CONTEXT

256k

AWS Bedrock

Amazon Nova Micro

The lowest-cost model in the AWS Bedrock lineup, for high-volume classification, extraction, and routing. Handles 128k tokens of context.

IN / 1M

$0.035

OUT / 1M

$0.14

CONTEXT

128k

AWS Bedrock

Meta Llama 3.3 70B Instruct

Lower-priced model for high-volume classification, extraction, and routing. Handles 128k tokens of context. 70B-parameter size in its family.

IN / 1M

$0.72

OUT / 1M

$0.72

CONTEXT

128k

AWS Bedrock

Meta Llama 3.1 70B Instruct

Lower-priced model for high-volume classification, extraction, and routing. Handles 128k tokens of context. 70B-parameter size in its family.

IN / 1M

$0.72

OUT / 1M

$0.72

CONTEXT

128k

AWS Bedrock

Meta Llama 3.1 8B Instruct

Lower-priced model for high-volume classification, extraction, and routing. Handles 128k tokens of context. 8B-parameter size in its family.

IN / 1M

$0.22

OUT / 1M

$0.22

CONTEXT

128k

BUILD WITH STEELENGINE

Put AWS Bedrock models to work.

Use these models in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.